Research Associate: Forecasting for Semiconductor Equipment

Nanyang Technological University Singapore; Singapore; On-site; SGD 45,000 - 70,000; Full time

Job summary

Nanyang Technological University (NTU)–NTI-NTU Corporate Laboratory is hiring a Research Associate to analyze equipment degradation time-series data and develop forecasting workflows using statistical, ML, and DL models. You will work with researchers and engineers to enable predictive maintenance in semiconductor operations.

Ideal candidates hold a strong background in materials science, electrical engineering, or physics, and have experience with Python-based data processing and time-series

Qualifications

• Masters in a closely related field with strong data analysis focus.
• Proficiency in Python for data processing and model development.
• Experience with time-series forecasting and semiconductor data is a plus.

Responsibilities

• Develop and apply time-series forecasting methods for equipment health monitoring.
• Analyze degradation data to support predictive maintenance and reliability studies.
• Implement and compare statistical, machine learning, and deep learning forecasting models.
• Preprocess data, perform signal smoothing, and analyze noise in real-world data.
• Evaluate model performance using forecasting metrics and visual analysis.
• Interpret results to determine forecasting usefulness given data limitations.
• Document findings and communicate insights to researchers and engineering teams.

Skills

Python

Time-series modeling

Data analysis

Education

Master's degree in Materials Science

Master's degree in Electrical/Electronic Engineering

Master's degree in Physics

Job description

Nanyang Technological University (NTU)–NTI-NTU Corporate Laboratory is hiring a Research Associate to analyze equipment degradation time-series data and develop forecasting workflows using statistical, ML, and DL models. You will work with researchers and engineers to enable predictive maintenance in semiconductor operations.

Ideal candidates hold a strong background in materials science, electrical engineering, or physics, and have experience with Python-based data processing and time-series